Abstract

Column-based databases generally stand out with their high-performance rates in big data environments where analytical queries are intensive. ClickHouse, as a column-based database system with open-source code and high-speed data query capacity, is among the solutions divided to meet many big data processing needs of the unit. Developments in open-source technologies in Turkey, ClickHouses usage rate in corporate structures is increasing. It is claimed that the ClickHouse database can provide much faster solutions compared to relational databases in large change data sets. In the study, an investigation was conducted to evaluate the performance of the ClickHouse database against varying data sizes. To obtain unbiased and repeatable performance metrics, datasets consisting of 1 million, 10 million, 50 million and 100 million records were prepared. Specific analytical queries and calculations were performed for each dataset, and the effect of the increase in data size on query times, resource usage and system efficiency were analyzed. Automation scripts were used to ensure consistent execution of queries, elimination of manual errors and systematic measurements. Data was visualized with the help of tables and graphs. Trends in performance and factors affecting system efficiency were revealed. As a result of the study, ClickHouses strengths and weaknesses under different workloads were determined. Findings were presented that will help researchers and system administrators choose the database system suitable for their usage scenarios.

References

[1] D. T. Montellano and S. T. D. Gravano, “High-Performance Columnar Databases for Real-Time Analytics: An Empirical Study,” Computers & Industrial Engineering, vol. 153, 107039, 2021. [2] Y. Liu and R. Chen, “Scaling Real-Time Analytics with ClickHouse: Storage, Query Execution, and Use Cases,” Future Generation Computer Systems, vol. 119, pp. 556–565, 2021.

[3] L. Shaw and M. Olteanu, “Performance and Optimization Strategies in Modern Columnar Database Systems: A Comprehensive Overview,” Journal of Parallel and Distributed Computing, vol. 157, pp. 98–108, 2021.

[4] A. Patel and A. Smith, “Columnar Data Store Performance Evaluation in Real-Time Analytics: A Case Study,” Journal of Big Data, vol. 11, no. 3, pp. 25–44, 2023.

[5] R. Johnson and T. D. White, “Challenges and Strategies for Distributed ClickHouse Clusters,” Data & Knowledge Engineering, vol. 141, 102898, 2023.

[6] H. Li and M. Xu, “Memory Management Optimization in Column-Oriented DBMS: Lessons from ClickHouse,” Information and Software Technology, vol. 151, 107035, 2023.

[7] S. Gupta and M. Ahmed, “Scalable Architecture for Real-Time Analytics with Columnar DBs: A Performance Exploration,” Computers & Industrial Engineering, vol. 187, 107934, 2024.

[8] J. Zhang, Q. Zhang, and C. Luo, “High-Speed Analytics with Columnar Databases for IoT Data Streams,” Future Generation Computer Systems, vol. 134, pp. 145–158, 2023.

[9] E. Diaz, L. Herrera, and G. Ramirez, “Storage Optimization in Modern Columnar Systems: A Comparative Study,” Information Systems, vol. 112, 102068, 2023.

[10] P. W. Sung, A. B. Kim, and J. Choi, “Evaluation of Real-Time Data Ingestion in Open-Source Column Stores: The Case of ClickHouse,” Journal of Parallel and Distributed Computing, vol. 173, pp. 124–136, 2023.

[11] Amazon Web Services, “Amazon EC2: Getting Started,” [Online]. Available:https://aws.amazon.com/tr/ec2/getting-started/. [Accessed: 01-Feb-2025].

[12] R. Schulze, T. Schreiber, I. Yatsishin, R. Dahimene, and A. Milovidov, "ClickHouse - Lightning Fast Analytics for Everyone," Proc. VLDB Endow., vol. 17, pp. 3731–3744, 2024.

[13] A. K. Dwivedi, C.S. Lamba, S. Shukla, “Performance Analysis of Column Oriented Database Versus Row Oriented Database,” International Journal of Computer Applications, vol. 50, pp. 31-34, July 2012.

[14] N. Jukic, B. Jukic, A. Sharma, S. Nestorov, and B. K. Arnold, "Expediting analytical databases with columnar approach," Decision Support Systems, vol. 95, pp. 61–81, Mar. 2017.

[15] ClickHouse, “Operations Overview,” ClickHouse Documentation, 2025. [Online]. Available: https://clickhouse.com/docs/operations/overview. [Accessed: Mar. 03, 2025].

[16] M.-E. Vasile, G. Avolio, and I. Soloviev, “Evaluating InfluxDB and ClickHouse database technologies for improvements of the ATLAS operational monitoring data archiving,” ResearchGate, 2020.